Smart Energy and Electric Power Systems: Current Trends and New Intelligent Perspectives

List of contributors
Preface
1 Smart power systems: an eyeview
1.1 Introduction to artificial intelligence
1.2 Necessity of artificial intelligence in power systems
1.3 Modern artificial intelligence techniques in power system
1.3.1 Artificial neural networks
1.3.2 Expert system techniques
1.3.3 Fuzzy logic (FL)
1.3.4 Genetic algorithm
1.4 Artificial intelligence techniques in smart grids
1.4.1 Load forecasting
1.4.2 Power grid stability analysis
1.4.3 Stability assessment
1.4.4 Rotor angle stability
1.4.5 Voltage stability
1.4.6 Frequency stability
1.4.7 Small signal stability
1.4.8 Transient stability
1.4.9 Stability control
1.4.10 Security assessment
1.4.11 Fault diagnosis
1.5 Challenges in smartgrid
1.5.1 Smart grid security challenges and objectives
1.5.2 High-level security requirements
1.5.3 Quality of service-related requirements
1.5.4 Transmission system
1.5.5 Distribution system
1.5.6 Telemetry infrastructure
References
2 Smart energy and electric power system: current trends and new intelligent perspectives and introduction to AI and power ...
2.1 Introduction
2.2 Power system
2.3 Overviews of artificial intelligence
2.4 Applications of artificial intelligence
2.4.1 Artificial intelligence in health care
2.4.2 Artificial intelligence in robotics
2.4.3 Artificial intelligence in gaming
2.4.4 Artificial intelligence in e-commerce
2.4.4.1 Personalized shopping
2.4.4.2 Fraud detection
2.4.4.3 Artificial intelligence in recruitment
2.5 Types of machine learning
2.6 Machine learning methods
2.6.1 Supervised learning methods
2.6.2 Unsupervised machine learning algorithms
2.6.3 Reinforcement machine learning algorithms
2.7 Deep learning and its types
2.8 Deep learning models
2.8.1 Autoencoder
2.8.2 Types of autoencoders
2.8.2.1 Convolution autoencoders
2.8.2.2 Sparse autoencoders
2.8.2.3 Deep autoencoders
2.9 Deep neural networks
2.10 Artificial neural networks
2.10.1 Artificial neural network characteristics
2.10.2 How artificial neural networks can be used in power systems
2.10.3 Applications
2.11 Convolution neural network
2.12 Fuzzy system
2.12.1 Fuzzy logic usage in power systems
2.12.2 Fuzzy controller
2.12.3 Applications
2.13 Expert systems in power system
2.13.1 Advantages
2.13.2 Disadvantage
2.13.3 Usage
2.14 Expert systems in power systems
2.14.1 Artificial intelligence in genetic algorithm
2.14.2 Advantages of genetic algorithm
2.14.3 Steps in genetic algorithm
2.14.4 Applications in power system
2.15 Genetic algorithms in power systems
2.16 Conclusion
References
3 Recent developments of smart energy networks and challenges
3.1 Introduction
3.2 Smart energy
3.3 Challenges in smart energy
3.4 Conclusion
References
4 A smart and efficient IoT-AI and ML-based multifunctional system for multilevel power distribution management
4.1 Introduction
4.1.1 Electricity meters, their varieties, and their history
4.2 Integration of Internet of things-artificial intelligence and machine learning toward power distribution and health mon...
4.3 Grid-assisted technology
4.3.1 Intelligent metering
4.3.2 Technology concerns
4.4 Transformer health monitoring from traditional till modern techniques
4.5 Forecast models toward consumer demand and stock analysis
4.5.1 Residential sector
4.5.2 Sector of commerce
4.5.3 Sector of industry
4.5.4 Agricultural sector
4.5.5 The government sector
4.6 Forecast models toward consumer demand and stock analysis
4.7 Transformer health monitoring from traditional till modern techniques
4.7.1 Transformer and distribution line health monitoring
4.7.2 Power quality and test analysis
4.7.3 Demand and supply chain
4.7.4 Generation and distribution management of power
4.7.5 Live time on a day
4.8 Conclusion
References
5 A survey on AI- and ML-based demand forecast analysis of power using IoT-based SCADA
5.1 Introduction
5.2 SCADA-based power consumption monitoring and metering systems
5.2.1 First-generation SCADA system
5.2.2 Second-generation SCADA system
5.2.3 Third-generation SCADA system
5.2.4 Fourth-generation SCADA system
5.3 Traditional power demand prediction method
5.3.1 Time series analysis using ARIMA and S-ARIMA (DSR)
5.3.2 Linear regression
5.4 Machine learning-based demand forecast analyst model
5.5 Deep learning-based demand forecast analytic model
5.6 Summary
5.7 Conclusion
References
Further reading
6 Impact of artificial intelligence techniques in distributed smart grid monitoring system
6.1 Introduction
6.2 Future energy system
6.3 Distributed smart grid monitoring system using artificial intelligence
6.3.1 Electricity trading and online load forecasting
6.3.2 Fault detection and protection in the power grid
6.3.3 Consumer energy usage behavior
6.3.4 Power network protection in smart grid
6.3.5 Distributed grid intelligence
6.3.5.1 Distributed intelligence: prosumer side
6.3.5.2 Generation side distributed intelligence
6.4 Artificial intelligence techniques for the integration of renewable energy system
6.4.1 Consumer-side renewable energy sources integration
6.4.2 Generation-side renewable energy sources integration
6.4.3 Integrating artificial intelligence into renewable energy sources
6.4.3.1 Smart supply-demand matching
6.4.3.2 Storage intelligence
6.4.3.3 Control system with centralized management
6.4.3.4 Intelligent microgrids
6.5 Artificial intelligence techniques for integration of energy storage system
6.5.1 Energy storage systems integration
6.5.1.1 Energy storage system integration: consumer side
6.5.1.2 Generation-side energy storage systems integration
6.6 Economic feature and market deregulation in smart grid (current trends)
6.7 Challenges and issues for implementation of artificial intelligence-based distributed smart grid monitoring system
6.8 Conclusion
References
7 Smart power quality control measures
7.1 Introduction
7.2 Cause of reduced power eminence
7.2.1 Voltage variety
7.2.2 Flicker
7.2.3 Energy spears or surge power
7.2.4 Overvoltage
7.2.5 Undervoltage
7.2.6 Disruption
7.2.7 Outage
7.2.8 Harmonics
7.2.9 Frequency fluctuation
7.2.10 Supply interruptions
7.3 Consequence of poor power quality
7.3.1 Regulating standards on electrical quality
7.3.2 Power quality standard for equipment
7.3.3 Power quality monitoring
7.3.4 Mitigation technique
7.3.5 Availability ensuring there is adequate power in the grid
7.3.6 Design of equipment
7.3.7 Interfacing devices
7.3.8 Filter
7.3.9 Proper grounding of the electrical system
7.4 Future: opportunities and regulatory problems
7.4.1 Identification of future challenges to power systems
7.4.2 Large volumes of data and heterogeneous data sources
7.4.3 Development of an end-user centric approach
7.4.4 Local energy transactions
7.4.5 High uncertainty in net load consumption balances and flows
7.5 Conclusion
References
8 Directional overcurrent relay coordination optimization
8.1 Introduction
8.2 Formulation of the coordination optimization problem
8.2.1 The objective function
8.2.2 The conventional inverse time relay characteristic
8.2.3 The dial and pickup setting constraints
8.2.4 The coordination constraints
8.3 The improved ant colony optimization
8.4 Improved ant colony optimization for protection coordination
8.4.1 AS matrix
8.4.2 Pheromone matrix
8.4.3 Transition rule
8.4.4 Pheromone updates
8.4.5 Improved ant colony optimization
8.5 Improved differential evolution for protection coordination
8.5.1 Initial population
8.5.2 Mutation
8.5.3 Crossover
8.5.4 Selection
8.5.5 Improved differential evolution
8.6 Results performance study among genetic algorithm, IACO and IDE
8.6.1 IEEE 14 bus system
8.7 Summary
Acknowledgments
Conflict of interest
References
9 Monitoring of wind power control in microgrid
9.1 Introduction
9.1.1 Monitoring of wind turbine includes the following factors
9.1.1.1 Need for modeling of power curve
9.1.1.2 Assessment of wind power and prediction
9.1.1.3 Capacity factor estimation
9.1.1.4 On-line supervision of power curves
9.1.2 Maintaining constant frequency and voltage
9.2 Problem statement
9.3 Methodology
9.3.1 Software design
9.3.2 Hardware design
9.3.2.1 Specifications of wind turbine
9.4 Implementation
9.4.1 Simulation of wind power system
9.4.1.1 Tip speed ratio
9.4.1.2 Turbine speed
9.4.1.3 Power output
9.4.1.4 Turbine direction
9.4.2 Simulation of substation
9.5 Simulation results
9.6 Conclusion
9.7 Future scope
Conflict of interest
References
10 Cyber attacks, security data detection, and critical loads in the power systems
10.1 Introduction
10.2 Cyber attacks in smart grids
10.2.1 Phishing
10.2.2 Denial-of-service
10.2.3 Malware spreading
10.2.4 Eavesdropping and traffic analysis
10.3 Smart grid cyber security needs and standards
10.3.1 Risk assessment
10.4 Proposed security solutions for smart grids
10.4.1 Encryption
10.4.2 Authentication
10.4.3 Malware protection
10.4.4 Network security
10.4.5 Remote access virtual private network
10.4.6 Site-to-site virtual private network
10.4.7 Intrusion detection systems and intrusion prevention system
10.4.8 Maturity assessments
References
11 Blockchain-based secured payment in IoE
11.1 Introduction
11.2 Blockchain
11.2.1 Working of blockchain
11.2.2 Decentralization
11.2.3 Integrity
11.2.4 Cryptography: fair to all
11.2.5 Security
11.2.6 Inclusive
11.2.7 Blockchain respects your privacy
11.2.8 Challenges in block chain
11.2.8.1 Scalability
11.2.8.2 Hackers and shadow dealing
11.2.8.3 Complex to understand and adopt
11.2.8.4 Privacy
11.2.8.5 Costs
11.2.8.6 Blockchain is still a distant dream
11.2.9 Application of block chain
11.2.9.1 Money transfers
11.2.9.2 Financial exchanges
11.2.9.3 Insurance
11.2.9.4 Real estate
11.2.9.5 Data storage
11.2.9.6 Gambling
11.3 Internet of everything (IoE)
11.3.1 Benefits of the Internet of things
11.3.2 Challenges in privacy and security
11.3.3 Communication between Machine to Machine
11.3.4 Application
11.3.4.1 Smart city
11.3.4.2 Smart grids
11.3.4.3 Health
11.3.4.4 Retail
11.3.4.5 Smart supply chain
11.3.4.6 Smart farming
11.4 Secure payments in IoE
11.4.1 IoE with blockchain: security challenges
11.4.2 A secures energy transaction prototype
11.4.3 Internet of entities (IoE): a blockchain-based distributed paradigm to security
11.4.4 A secured blockchain prototype
11.4.5 Role of software in securing Internet of things/IoE
11.4.6 Role of IoE/Internet of things in vehicular networks
11.4.7 IoE with privacy
11.4.8 Physical unclonable function enabled secured blockchain
References
Index